© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 38813
    Prev
    Next
    INDEX
    Explanations

    learning and creativity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.3-70B-IT @ 50-resid-post-gf
    Configuration
    Goodfire/Llama-3.3-70B-Instruct-SAE-l50/Llama-3.3-70B-Instruct-SAE-l50.pt
    Prompts (Dashboard)
    10,000 prompts, 128 tokens each
    Dataset (Dashboard)
    lmsys/lmsys-chat-1m
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Reed
    -0.09
     thing
    -0.09
     pockets
    -0.09
     tad
    -0.08
    alc
    -0.08
     aver
    -0.08
     rel
    -0.08
     Prism
    -0.08
     wink
    -0.08
     ext
    -0.08
    POSITIVE LOGITS
     pixels
    0.10
     Pixels
    0.09
    eniable
    0.09
    LayoutPanel
    0.09
    estre
    0.09
     digits
    0.09
    Pixels
    0.09
     Tweets
    0.09
     Spielberg
    0.08
     electrons
    0.08
    Activations Density 0.144%

    No Known Activations